Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add luxiaolei/graph-engineering --skill graph-engineeringgit clone --depth 1 https://github.com/luxiaolei/graph-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/luxiaolei/graph-engineering/graph-engineering)<a href="https://agentmods.dev/skills/luxiaolei/graph-engineering/graph-engineering"><img src="https://agentmods.dev/badge/skills/luxiaolei/graph-engineering/graph-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/luxiaolei/graph-engineering/graph-engineering"><img src="https://agentmods.dev/badge/skills/luxiaolei/graph-engineering/graph-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01881 |
| Opus 5.5 | $0.00030 | $0.00752 |
| Sonnet 5.5 | $0.00015 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
graph-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Engineering
Design the smallest project-local Graph contract that matches the workflow's actual risk. Do not build a graph runtime and do not execute the target business workflow.
Select the mode and risk tier
- Create establishes a new durable or repeatable workflow.
- Audit checks an existing
.codex/graphscontract without editing it. - Evolve changes a Skill, Agent, or Graph from measured execution evidence.
Derive Graph necessity from the action facts before asking any question. A
user-authorized, one-time, bounded, reversible local task with
actual_authority_effect=none is NO_GRAPH: proceed under repository rules
and do not ask to create or evolve a Graph. Durable, repeatable, or
authority-changing work may justify a Graph.
When a Graph is justified, choose the lowest sufficient tier:
| Tier | Use when | Extra control plane |
|---|---|---|
workflow-lite/v1 or no profile |
reversible local workflow; low blast radius | base Graph only |
reviewed-batch/v1 |
material code or governed-artifact batch | one immutable-batch review, repair limit 0 or 1, one terminal record |
authority-critical/v1 |
data admission, sealed evidence/OOS consumption, broker or trading authority, irreversible publication, secrets/permissions, or comparable blast radius | closed admission pack, exact bounded review, serial integration, terminal seal |
governed-implementation/v1 is validation-only legacy compatibility; never
use it in a new proposal or template. Do not select an authority-critical profile merely
because a task is complex, long-running, or important.
Read discovery before create/evolve, the contract before writing Graph files, Codex mapping before defining delegated roles, governance for evolve work or external side effects, and multi-repo guidance when more than one repository is in scope.
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 206 B
- assets/templates/AGENTS.graph-engineering.md 992 B
- assets/templates/evolution-proposal.md 1.0 KB
- assets/templates/graph-authority-critical.md 11 KB
- assets/templates/GRAPH-ENGINEERING-BOUNDARY.md 320 B
- assets/templates/graph-reviewed-batch.md 3.8 KB
- assets/templates/graph.md 2.9 KB
- assets/templates/INDEX.md 2.1 KB
- assets/templates/lifecycle-witness.json 2.2 KB
- assets/templates/managed-supervisor-prompt.md 3.6 KB
- assets/templates/stable-agent.toml 631 B
- assets/templates/task-admission-pack.yaml 1.5 KB
- assets/templates/TOPOLOGY.md 502 B
- assets/templates/witness-blocked.json 153 B
- assets/templates/witness-final-rereview.json 161 B
- assets/templates/witness-initial-review.json 161 B
- assets/templates/witness-peer-root-portability.json 168 B
- assets/templates/witness-repair.json 153 B
- assets/templates/witness-review-materialization.json 173 B
- assets/templates/witness-success.json 153 B
- assets/templates/witness-terminal-seal.json 158 B
- references/codex-runtime.md 8.0 KB
- references/discovery.md 3.0 KB
- references/evolution-governance.md 2.3 KB
- references/graph-contract.md 14 KB
- references/multi-repo.md 1.7 KB
- scripts/generate_managed_supervisor_prompt.py 4.7 KB runs code
- scripts/integrate_supervisor_guidance.py 1.8 KB runs code
- scripts/validate_project_graph.py 113 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 154 lines · 75 tokens per session scan A a9942747dc66
graph-engineering is a skill published in the GitHub repository luxiaolei/graph-engineering (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,881 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
antigravity-cli
Use Antigravity CLI as a subagent. Lets the main agent prompt Antigravity CLI from the terminal in headless mode with the agy command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Antigravity CLI, when a task needs a second independent agent, or when a plan…
claude-code
Use Claude Code CLI as a subagent. Lets the main agent prompt Claude Code CLI from the terminal in headless mode with the claude command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Claude Code CLI, when a task needs a second independent agent, or when a…
codex-cli
Use Codex CLI as a subagent. Lets the main agent prompt Codex CLI from the terminal in headless mode with the codex command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Codex CLI, when a task needs a second independent agent, or when a plan needs a fresh…
copilot-cli
Use GitHub Copilot CLI as a subagent. Lets the main agent prompt GitHub Copilot CLI from the terminal in headless mode with the copilot command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to GitHub Copilot CLI, when a task needs a second independent agent, or…
junie-cli
Use Junie CLI as a subagent. Lets the main agent prompt Junie CLI from the terminal in headless mode with the junie command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Junie CLI, when a task needs a second independent agent, or when a plan needs a fresh…
opencode-cli
Use OpenCode CLI as a subagent. Lets the main agent prompt OpenCode CLI from the terminal in headless mode with the opencode command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to OpenCode CLI, when a task needs a second independent agent, or when a plan needs…